© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58004
    Prev
    Next
    INDEX
    Explanations

    http links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħĭéļ¾
    -0.08
    ervis
    -0.08
    ä¸įæĸŃæĽ´æĸ°
    -0.07
    лки
    -0.07
    .dat
    -0.07
    CommandEvent
    -0.07
    uka
    -0.07
    Boy
    -0.07
     soundtrack
    -0.07
    hub
    -0.07
    POSITIVE LOGITS
    彬
    0.08
    ajo
    0.07
    å³¥
    0.07
    леб
    0.07
    obuf
    0.07
    ÙĦاÙħ
    0.07
    åį·
    0.06
    usher
    0.06
     intr
    0.06
    èĦijåIJİ
    0.06
    Activations Density 0.003%

    No Known Activations